How to Use the Braintree MCP in LlamaIndex

Q: Can LlamaIndex index Braintree refund data?

Yes, the output from refundtransaction can be written directly to your vector index. This lets you query refund histories semantically during customer support chats.

Q: How does LlamaIndex prevent calling the wrong Braintree tool?

You can use the allowedtools filter during setup to restrict agent access. This ensures your RAG pipeline only calls search tools and cannot run write actions like chargepaymentmethod.

Q: Can I search transactions without indexing everything?

Yes, the agent can call searchtransactions directly as an on-demand MCP tool. It only indexes the specific results returned from that search query.

Index Braintree transaction data directly into your LlamaIndex RAG pipelines for grounded financial reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Braintree MCP to LlamaIndex

Create your Vinkius account to connect Braintree to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Braintree with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Braintree records in LlamaIndex

The `get_transaction` tool pulls raw payment data directly into your LlamaIndex document store. The framework converts these transaction details into queryable nodes, ensuring your agent answers financial questions using real database records. This setup eliminates hallucinated transaction numbers. Your agent queries the local vector store first, verifying past payment states before running actions like `void_transaction` on an active authorization.

Ground LlamaIndex queries in Braintree customer data

The `get_customer` tool retrieves customer details to update your vector index dynamically using the MCP Server. By loading these profiles into LlamaIndex, your agent cross-references user histories to answer complex support queries accurately. You can run `search_customers` to find patterns across multiple accounts. The retrieved documents feed directly into the index, giving your RAG application a clear view of your active user base.

Match historical transactions to support tickets

The `search_transactions` tool queries your payment history to resolve customer disputes. The tool outputs are indexed as semantic nodes, letting your agent instantly match a user's chat message to a specific transaction. If the user requests a reversal, the agent uses the indexed context to call `refund_transaction` with the correct transaction ID. This keeps the entire support loop grounded in actual payment history.

Setup guide

Set up Braintree MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Braintree MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Braintree tools.",
)
response = await agent.run("List recent Braintree data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Braintree. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Braintree now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Braintree MCP in LlamaIndex

You initialize the BasicMCPClient and wrap it with McpToolSpec. Then, call to_tool_list_async to generate the tool list for your LlamaIndex FunctionAgent.

Yes, the output from refund_transaction can be written directly to your vector index. This lets you query refund histories semantically during customer support chats.

You can use the allowed_tools filter during setup to restrict agent access. This ensures your RAG pipeline only calls search tools and cannot run write actions like charge_payment_method.

Yes, the agent can call search_transactions directly as an on-demand MCP tool. It only indexes the specific results returned from that search query.

All payment tokens are processed in ephemeral, isolated runtime environments. Your credentials and transaction amounts are never persisted or exposed to outside networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript